RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information

TL;DR

RESIDE enhances distantly-supervised neural relation extraction by leveraging side information like entity types and relation aliases, using GCNs to encode syntactic info, leading to improved performance on benchmark datasets.

Contribution

It introduces RESIDE, a novel method that incorporates side information and GCNs to improve relation extraction accuracy in distantly-supervised settings.

Findings

RESIDE outperforms baseline models on benchmark datasets.

Utilizing side information significantly improves extraction accuracy.

GCN encoding of syntactic info enhances model robustness.

Abstract

Distantly-supervised Relation Extraction (RE) methods train an extractor by automatically aligning relation instances in a Knowledge Base (KB) with unstructured text. In addition to relation instances, KBs often contain other relevant side information, such as aliases of relations (e.g., founded and co-founded are aliases for the relation founderOfCompany). RE models usually ignore such readily available side information. In this paper, we propose RESIDE, a distantly-supervised neural relation extraction method which utilizes additional side information from KBs for improved relation extraction. It uses entity type and relation alias information for imposing soft constraints while predicting relations. RESIDE employs Graph Convolution Networks (GCN) to encode syntactic information from text and improves performance even when limited side information is available. Through extensive experiments on benchmark datasets, we demonstrate RESIDE's effectiveness. We have made RESIDE's source code available to encourage reproducible research.